Experiments on the Choice of Features for Learning Verb Classes
نویسنده
چکیده
The choice of verb features is crucial for the learning of verb classes. This paper presents clustering experiments on 168 German verbs, which explore the relevance of features on three levels of verb description, purely syntactic frame types, prepositional phrase information and selectional preferences. In contrast to previous approaches concentrating on the sparse data problem, we present evidence for a linguistically defined limit on the usefulness of features which is driven by the idiosyncratic properties of the verbs and the specific attributes of the desired verb classification.
منابع مشابه
رشد جنبه معنایی فعل در کودک فارسیزبان: مطالعه طولی
Objective Learning “verb” as one of the main components of sentence, has been always a debatable topics in the process of language learning. One of the important issues in “verb” learning is determining its meaning using syntactic clues and learning its semantic aspects. Therefore, the main objective of this study was to examine the development of the semantic aspect of ...
متن کاملThe Effect of Using Keyword Method on EFL Learners' Learning and Retrieving English Verb Types
This study used keyword method during encoding information in transferring information from short term memory to make the retrieval easier. For this purpose, 50 adult female elementary students were chosen to participate in this study. This study required two groups of learners (control and experimental groups). The experimental group enjoyed some special flashcards which each of them involved ...
متن کاملTwo modes of assessment: the case of academicians' writing
This study attempted to investigate writing problems and the relationship between expert-assessment and self-assessment of writing problems. Participants were thirty four non-English faculty members of Tehran and Guilan universities. The instruments were writing an essay on the topic "What teaching strategies do you use in your classes?" in twenty five lines and filling the questionnaire of wri...
متن کاملVerb Classification – Machine Learning Experiments in Classifying Verbs into Semantic Classes
This paper presents the results of our machine learning experiments in verb classification. Using Beth Levin’s semantic classification of the English verbs as a gold standard, we (i) test the hypothesis that the syntactic behavior of a verb can be used to predict its semantic class, and (ii) investigate whether a robust shallow parser can provide the necessary syntactic information. With 277 ve...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2003